Sentinel surveillance applications are very important since this is the way the perimeter of military base needs to maintain in a secure state. The surveillance systems based on infrared and visible sensors technology are widely used because they can work well under poor lighting conditions. In this paper, a fusion scheme of infrared and visible images is proposed for detecting targets. A simple and efficient image fusion approach based on the application of the histogram of infrared images is adopted. The fusion scheme to select adaptively weighted coefficients for preserving salient infrared targets coming from the infrared image and for obtaining mostly spatial detail information from the visible image is presented. Moving and static infrared targets in the fused image are labeled with different colors. This enhances perception of the image by the human visual system. In view of the modalities of infrared images, low resolution, and low signal-to-noise ratio, an anisotropic diffusionrnequation model is adopted for removing noise and effectively preserving edgerninformation before the fusion stage. In our experiments, the fusion results demonstrate that fused images using our method can preserve high spatial relevant information and clearly show infrared targets. Moving and static infrared targets are marked with different colors, which is helpful for sentinel surveillance.
展开▼